openprotein

This document describes the base dataclasses and primitives for working with the platform.

This includes the OpenProtein session object, as well as primitives like the Protein and Model objects.

Session

Create an authorized session to OpenProtein.AI backend.

openprotein.connect(username=None, password=None, backend='https://api.openprotein.ai/api/', timeout=180)

The base class for accessing OpenProtein API functionality.

class openprotein.OpenProtein(username=None, password=None, backend='https://api.openprotein.ai/api/', timeout=180)

The base class for accessing OpenProtein API functionality.

property data: DataAPI

The data submodule gives access to functionality for uploading and accessing user data.

property jobs: JobsAPI

The jobs submodule gives access to functionality for listing jobs and checking their status.

property align: AlignAPI

The Align submodule gives access to the sequence alignment capabilities by building MSAs and prompts that can be used with PoET.

property prompt: PromptAPI

The Align submodule gives access to the sequence alignment capabilities by building MSAs and prompts that can be used with PoET.

property embedding: EmbeddingsAPI

The embedding submodule gives access to protein embedding models and their inference endpoints.

property embeddings: EmbeddingsAPI

The embedding submodule gives access to protein embedding models and their inference endpoints.

property svd: SVDAPI

The embedding submodule gives access to protein embedding models and their inference endpoints.

property umap: UMAPAPI

The embedding submodule gives access to protein embedding models and their inference endpoints.

property predictor: PredictorAPI

The predictor submodule gives access to training and predicting with predictors built on top of embeddings.

property design: DesignAPI

The designer submodule gives access to functionality for designing new sequences using models from predictor train.

property fold: FoldAPI

The fold submodule gives access to functionality for folding sequences and returning PDBs.

property models: ModelsAPI

The models submodule provides a unified entry point to all protein models.

Data Primitives

These data primitives represent a unified interface to working with our platform, whether it be structure prediction, binder design or inverse folding.

Protein

Protein is a fundamental primitive for working with proteins on the platform. These can be uploaded to our platform as a Query to be used with models like ProteinMPNNModel (e.g. for inverse-folding), as well as for ease of reuse.

Model

Model describes a multimer representation. These can be uploaded to our platform as a Query to be used with models like RFdiffusionModel, (e.g. for multi-chain binder design) as well as for easy reuse.

Ligand

Ligand represents a ligand that can be described either by smiles or ccd. These are intended to be used as part of a Model.

DNA

DNA represents a DNA chain. These are intended to be used as part of a Model.

RNA

RNA represents a RNA chain. These are intended to be used as part of a Model.